RETRACTED: User Power Interaction Behavior Clustering Analysis That is Based on the Self-Organizing-Center K-Means Algorithm (Retracted Article)

The participation of power users in grid-side interactive power and auxiliary services has attracted increasing attention. The analysis of users' interaction power behaviors is a core task. By combining the self-organizing map (SOM) neural network and the K-means clustering algorithm, a self-organizing-center K-means algorithm is developed in this paper for conducting a cluster analysis of users' interaction electricity consumption behaviors. This approach can realize more accurate recognition and fast clustering. First, the principle of K-means algorithm in the self-organizing center is analyzed, and its advantages in the clustering analysis of electricity consumption over the traditional clustering algorithm are demonstrated. Then, in the context of peak-to-valley time-of-use electricity pricing, the adjustment potential index, which is based on user psychology, is developed, and a cluster analysis of users' electricity consumption behaviors that is based on load data and the adjustment potential index is conducted. Finally, the daily load data of users within the jurisdiction of a power company are studied, and the two-stage clustering results that are obtained via the self-organizing-center K-means algorithm are compared with the clustering results that are obtained via the K-means algorithm, which demonstrates the advantages of the self-organizing-center K-means algorithm that is based on the adjustment potential index in the accurate recognition and accurate clustering of users.